Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/lf-decentralized-trust-labs/gitmesh/agents-mdgit clone --depth 1 https://github.com/LF-Decentralized-Trust-labs/gitmeshWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/lf-decentralized-trust-labs/gitmesh/agents-md)<a href="https://agentmods.dev/instructions/lf-decentralized-trust-labs/gitmesh/agents-md"><img src="https://agentmods.dev/badge/instructions/lf-decentralized-trust-labs/gitmesh/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01129 | $0.01129 |
| Opus 5 | $0.00564 | $0.00564 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
gitmesh AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitMesh: Instructions for Coding Agents
Status: repository pivot in progress
GitMesh is pivoting from a multi-agent orchestration runtime to the Agent
Workspace Compiler: a single CLI + GitHub Action that audits (doctor),
compiles (apply), drift-checks (check), and enforces (policy)
coding-agent configuration from the repo. No server, no database, no daemon
in the new product.
Before any work, read doc/pivot/pivot.md (the canonical plan) and
doc/pivot/research_results.md (the evidence). If anything in this repository,
including this file, contradicts doc/pivot/pivot.md, the pivot doc wins.
How to work
- Implement the task backlog in
doc/pivot/pivot.md§12 strictly in order, starting from the first unfinished task. One task = one branch/PR. - Meet the task's acceptance criteria and add its tests before moving on. Never batch tasks, never skip ahead, never start a task the previous one hasn't unblocked.
- If the plan is ambiguous, or reality contradicts it (an agent vendor changed a config format since 2026-07-19), stop and ask the maintainer, citing the pivot section number. Never improvise silently on plan-level decisions.
Repository map
| Area | Status | Notes |
|---|---|---|
cli/ |
ACTIVE | becomes the gitmesh CLI (doctor, init, migrate, apply, check, policy); legacy commands move under gitmesh legacy (task T0.3) |
lib/workspace-core/ |
ACTIVE (new) | IR, normalizer, GM risk rules, lockfile, marker/merge engine |
lib/workspace-adapters/ |
ACTIVE (new) | per-agent adapters: detect / import / plan / emit + golden fixtures. (Planned as lib/adapters/ in doc/pivot/pivot.md §10.8/T0.2; renamed because that directory already holds the frozen legacy runtime adapters. Maintainer decision, 2026-07-19) |
existing lib/ code (OPA policy compiler, MCP/ACP parsers, Ed25519 attestation, forge clients) |
REUSE | repurpose per doc/pivot/pivot.md §9.1: do not rewrite wholesale, do not delete |
server/, ui/, docker/, playbooks/, agents/, heartbeat / Postgres / webhook code |
FROZEN | do not modify, refactor, "clean up", or delete anything here |
doc/, docs/ |
docs | doc/pivot/pivot.md is canonical; server-era docs (doc/SETUP.md, doc/DEVELOPING.md, docker-compose files) are legacy, so do not follow them for pivot work |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 78 lines · 1,129 tokens per session scan A ebb46acbd74f
gitmesh AGENTS.md is an instructions file published in the GitHub repository LF-Decentralized-Trust-labs/gitmesh (145 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,129 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
windmill AGENTS.md
AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.